Learning to generate chairs with convolutional neural networks

作者：Alexey Dosovitskiy, Jost Tobias Springenberg, Thomas Brox · 年份：2015 · DOI：10.1109/cvpr.2015.7298761 · 被引用次数：684 · 研究领域：Face recognition and analysis、Generative Adversarial Networks and Image Synthesis、Video Surveillance and Tracking Methods

We train a generative convolutional neural network which is able to generate images of objects given object type, viewpoint, and color. We train the network in a supervised manner on a dataset of rendered 3D chair models. Our experiments show that the network does not merely learn all images by heart, but rather finds a meaningful representation of a 3D chair model allowing it to assess the similarity of different chairs, interpolate between given viewpoints to generate the missing ones, or invent new chair styles by interpolating between chairs from the training set. We show that the network can be used to find correspondences between different chairs from the dataset, outperforming existing approaches on this task.